summaryrefslogtreecommitdiff
path: root/ggml-vulkan.cpp
diff options
context:
space:
mode:
authorslaren <slarengh@gmail.com>2024-03-18 11:03:04 +0100
committerGitHub <noreply@github.com>2024-03-18 11:03:04 +0100
commit2bf8d0f7c4cc1235755ad06961ca761e458c5e55 (patch)
treed2a462deb3c0e34cfb26eab6881a65bfb9fc3b28 /ggml-vulkan.cpp
parent496bc79bc2b79bfd6124b8687a8dbd6a646e9b06 (diff)
backend : offload large batches to GPU (#6083)
* backend : offload large batches to GPU * fix hip * code cleanup * fix CUDA split buffers * Update ggml-backend-impl.h Co-authored-by: Johannes Gäßler <johannesg@5d6.de> * cuda : fix memset without set_device * imatrix : remove sched affix from weight names * sched : add a new split if the current one has too many inputs reduce max inputs per split more cleanup * update backends ggml-ci --------- Co-authored-by: Johannes Gäßler <johannesg@5d6.de>
Diffstat (limited to 'ggml-vulkan.cpp')
-rw-r--r--ggml-vulkan.cpp1
1 files changed, 1 insertions, 0 deletions
diff --git a/ggml-vulkan.cpp b/ggml-vulkan.cpp
index 698b3149..cbceaa19 100644
--- a/ggml-vulkan.cpp
+++ b/ggml-vulkan.cpp
@@ -5699,6 +5699,7 @@ static ggml_backend_i ggml_backend_vk_interface = {
/* .graph_plan_compute = */ NULL,
/* .graph_compute = */ ggml_backend_vk_graph_compute,
/* .supports_op = */ ggml_backend_vk_supports_op,
+ /* .offload_op = */ NULL,
/* .event_new = */ NULL,
/* .event_free = */ NULL,
/* .event_record = */ NULL,